Wayne Luk

3 papers · 2020–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (15)

Venues

EMNLP (1) ICCV (1) IJCAI (1)

Top co-authors

Hao Mark Chen (2) Hongxiang Fan (2) Shell Xu Hu (1) Brian Vogel (1) Rui Li (1) Konstantin Mishchenko (1) Ruizhe Zhao (1) Stylianos Venieris (1) Yiu Ka Fai Cedric (1) Tanvir Ahmed (1)

Research topics

Deep Learning (3) Machine Learning (3) Optimization & Theory · Deep Learning (3) Artificial Intelligence (2) Application Areas (2) Core AI (2) Optimization & Theory · Machine Learning (2) Mathematics & Optimization (1) Learning Paradigms (1) Learning Types (1) Optimization (1) Techniques (1)

Keywords

model compression (1) multi-task learning (1) knowledge distillation (1) model merging (1) constrained optimization (1) continuous optimization (1) model inference (1) memory efficiency (1) numerical stability (1) inference optimization (1) speculative decoding (1) mixed precision training (1) parallel decoding (1) hardware optimization (1) frank-wolfe optimization (1) large language model (1) gradient scaling (1) half precision floating point (1) gradient underflow (1) floating point (1)

Papers

FW-Merging: Scaling Model Merging with Frank-Wolfe Optimization ICCV 2025 Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference EMNLP 2025 Reducing Underflow in Mixed Precision Training by Gradient Scaling IJCAI 2020